Performance & Quality
Open-Weight Leaderboard
Rank open models using public hub momentum, public benchmark sources, and open model metadata.
How to use this dashboard
Rank open models using public hub momentum, public benchmark sources, and open model metadata.
Use this leaderboard to compare open-weight models by public quality signals, model hub traction, and practical deployment clues. Treat downloads and likes as popularity signals, not quality scores.
Open-Weight Leaderboard
80 records| 19 | deepseek-ai/DeepSeek-R1 | deepseek-ai | mit | Not listed | 137056658 | 3,896,658 | 13,316 | text-generation |
| 22 | meta-llama/Meta-Llama-3-8B | meta-llama | llama3 | 8B | 68533766 | 3,293,766 | 6,524 | text-generation |
| 7 | meta-llama/Llama-3.1-8B-Instruct | meta-llama | llama3.1 | 8B | 67073753 | 9,393,753 | 5,768 | text-generation |
| 12 | openai/gpt-oss-20b | openai | apache-2.0 | 20B | 52217411 | 6,507,411 | 4,571 | text-generation |
| 20 | openai/gpt-oss-120b | openai | apache-2.0 | 120B | 51180123 | 3,710,123 | 4,747 | text-generation |
| 2 | openai-community/gpt2 | openai-community | mit | Not listed | 47534081 | 15,304,081 | 3,223 | text-generation |
| 51 | meta-llama/Meta-Llama-3-8B-Instruct | meta-llama | llama3 | 8B | 46470355 | 1,500,355 | 4,497 | text-generation |
| 79 | mistralai/Mistral-7B-v0.1 | mistralai | apache-2.0 | 7B | 41838187 | 1,038,187 | 4,080 | text-generation |
| 77 | deepseek-ai/DeepSeek-V3 | deepseek-ai | Not listed | Not listed | 41675642 | 1,045,642 | 4,063 | text-generation |
| 34 | mistralai/Mistral-7B-Instruct-v0.2 | mistralai | apache-2.0 | 7B | 33361526 | 2,091,526 | 3,127 | text-generation |
| 1 | Qwen/Qwen3-0.6B | Qwen | apache-2.0 | 0.6B | 30647766 | 18,497,766 | 1,215 | text-generation |
| 4 | deepseek-ai/DeepSeek-V3.2 | deepseek-ai | mit | Not listed | 25530376 | 11,290,376 | 1,424 | text-generation |
| 3 | Qwen/Qwen2.5-7B-Instruct | Qwen | apache-2.0 | 7B | 25327932 | 12,847,932 | 1,248 | text-generation |
| 58 | meta-llama/Llama-3.2-1B | meta-llama | llama3.2 | 1B | 25127544 | 1,377,544 | 2,375 | text-generation |
| 39 | meta-llama/Llama-2-7b-hf | meta-llama | llama2 | 7B | 24856325 | 1,896,325 | 2,296 | text-generation |
| 53 | meta-llama/Llama-3.1-8B | meta-llama | llama3.1 | 8B | 23208140 | 1,468,140 | 2,174 | text-generation |
| 36 | meta-llama/Llama-3.2-3B-Instruct | meta-llama | llama3.2 | 3B | 23105766 | 1,945,766 | 2,116 | text-generation |
| 61 | Qwen/Qwen2.5-Coder-32B-Instruct | Qwen | apache-2.0 | 32B | 21424131 | 1,304,131 | 2,012 | text-generation |
| 9 | Qwen/Qwen3-8B | Qwen | apache-2.0 | 8B | 19694066 | 9,024,066 | 1,067 | text-generation |
| 17 | meta-llama/Llama-3.2-1B-Instruct | meta-llama | llama3.2 | 1B | 19371491 | 5,501,491 | 1,387 | text-generation |
| 23 | TinyLlama/TinyLlama-1.1B-Chat-v1.0 | TinyLlama | apache-2.0 | 1.1B | 18942664 | 3,192,664 | 1,575 | text-generation |
| 5 | Qwen/Qwen3-4B-Instruct-2507 | Qwen | apache-2.0 | 4B | 18138900 | 9,888,900 | 825 | text-generation |
| 27 | vikhyatk/moondream2 | vikhyatk | apache-2.0 | Not listed | 16722283 | 2,642,283 | 1,408 | image-text-to-text |
| 6 | Qwen/Qwen2.5-1.5B-Instruct | Qwen | apache-2.0 | 1.5B | 16652742 | 9,832,742 | 682 | text-generation |
| 72 | deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | deepseek-ai | mit | 32B | 16641586 | 1,121,586 | 1,552 | text-generation |
| 16 | Qwen/Qwen3-Embedding-0.6B | Qwen | apache-2.0 | 0.6B | 15698639 | 5,678,639 | 1,002 | feature-extraction |
| 88 | MiniMaxAI/MiniMax-M2.5 | MiniMaxAI | other | Not listed | 15574475 | 924,475 | 1,465 | text-generation |
| 8 | Qwen/Qwen2.5-3B-Instruct | Qwen | other | 3B | 13661908 | 9,171,908 | 449 | text-generation |
| 28 | Qwen/Qwen3-Coder-30B-A3B-Instruct | Qwen | apache-2.0 | 30B | 12951330 | 2,601,330 | 1,035 | text-generation |
| 14 | Qwen/Qwen3-4B | Qwen | apache-2.0 | 4B | 12294721 | 6,234,721 | 606 | text-generation |
| 13 | Qwen/Qwen2.5-0.5B-Instruct | Qwen | apache-2.0 | 0.5B | 11328199 | 6,278,199 | 505 | text-generation |
| 15 | Qwen/Qwen3-1.7B | Qwen | apache-2.0 | 1.7B | 10617216 | 6,077,216 | 454 | text-generation |
| 35 | deepseek-ai/DeepSeek-R1-Distill-Llama-8B | deepseek-ai | mit | 8B | 10560634 | 1,990,634 | 857 | text-generation |
| 64 | Qwen/Qwen3-30B-A3B | Qwen | apache-2.0 | 30B | 10113981 | 1,283,981 | 883 | text-generation |
| 10 | facebook/opt-125m | other | 125M | 9902577 | 7,422,577 | 248 | text-generation | |
| 29 | Qwen/Qwen3-32B | Qwen | apache-2.0 | 32B | 9504844 | 2,594,844 | 691 | text-generation |
| 32 | Qwen/Qwen2.5-Coder-7B-Instruct | Qwen | apache-2.0 | 7B | 9140579 | 2,140,579 | 700 | text-generation |
| 75 | Qwen/Qwen3-30B-A3B-Instruct-2507 | Qwen | apache-2.0 | 30B | 9127192 | 1,077,192 | 805 | text-generation |
| 26 | distilbert/distilgpt2 | distilbert | apache-2.0 | Not listed | 8950876 | 2,700,876 | 625 | text-generation |
| 49 | microsoft/Phi-3.5-vision-instruct | microsoft | mit | Not listed | 8888460 | 1,568,460 | 732 | image-text-to-text |
| 52 | microsoft/Phi-4-mini-instruct | microsoft | mit | Not listed | 8810838 | 1,490,838 | 732 | text-generation |
| 74 | meta-llama/Llama-3.2-3B | meta-llama | llama3.2 | 3B | 8726595 | 1,096,595 | 763 | text-generation |
| 57 | nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | nvidia | other | 30B | 8650603 | 1,410,603 | 724 | text-generation |
| 37 | Qwen/Qwen3-Embedding-8B | Qwen | apache-2.0 | 8B | 8592006 | 1,902,006 | 669 | feature-extraction |
| 96 | lightonai/LightOnOCR-2-1B | lightonai | apache-2.0 | 1B | 7531415 | 831,415 | 670 | image-text-to-text |
| 11 | trl-internal-testing/tiny-Qwen2ForCausalLM-2.5 | trl-internal-testing | Not listed | Not listed | 7260892 | 7,210,892 | 5 | text-generation |
| 82 | deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct | deepseek-ai | other | Not listed | 6902522 | 1,012,522 | 589 | text-generation |
| 25 | Qwen/Qwen3-14B | Qwen | apache-2.0 | 14B | 6748438 | 2,858,438 | 389 | text-generation |
| 91 | Qwen/Qwen3-4B-Thinking-2507 | Qwen | apache-2.0 | 4B | 6703386 | 893,386 | 581 | text-generation |
| 43 | nvidia/Gemma-4-31B-IT-NVFP4 | nvidia | other | 31B | 6171495 | 1,851,495 | 432 | text-generation |
| 42 | Qwen/Qwen2.5-0.5B | Qwen | apache-2.0 | 0.5B | 5832676 | 1,852,676 | 398 | text-generation |
| 30 | Qwen/Qwen2.5-14B-Instruct | Qwen | apache-2.0 | 14B | 5772077 | 2,462,077 | 331 | text-generation |
| 31 | openai-community/gpt2-large | openai-community | mit | Not listed | 5744823 | 2,254,823 | 349 | text-generation |
| 21 | Qwen/Qwen2-1.5B-Instruct | Qwen | apache-2.0 | 1.5B | 5205611 | 3,585,611 | 162 | text-generation |
| 18 | dphn/dolphin-2.9.1-yi-1.5-34b | dphn | apache-2.0 | 34B | 5159015 | 4,539,015 | 62 | text-generation |
| 55 | Qwen/Qwen3-Reranker-0.6B | Qwen | apache-2.0 | 0.6B | 4858958 | 1,418,958 | 344 | text-ranking |
| 69 | Qwen/Qwen2.5-32B-Instruct | Qwen | apache-2.0 | 32B | 4635345 | 1,155,345 | 348 | text-generation |
| 56 | HuggingFaceTB/SmolLM2-135M-Instruct | HuggingFaceTB | apache-2.0 | 135M | 4536913 | 1,416,913 | 312 | text-generation |
| 46 | Qwen/Qwen2.5-7B | Qwen | apache-2.0 | 7B | 4495561 | 1,685,561 | 281 | text-generation |
| 44 | Qwen/Qwen3-Embedding-4B | Qwen | apache-2.0 | 4B | 4352972 | 1,772,972 | 258 | feature-extraction |
| 95 | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | nvidia | other | 120B | 3727172 | 877,172 | 285 | text-generation |
| 24 | EleutherAI/pythia-160m | EleutherAI | apache-2.0 | 160M | 3513336 | 3,103,336 | 41 | text-generation |
| 47 | Qwen/Qwen2.5-Coder-7B | Qwen | apache-2.0 | 7B | 3096748 | 1,676,748 | 142 | text-generation |
| 66 | HuggingFaceTB/SmolLM2-135M | HuggingFaceTB | apache-2.0 | 135M | 3082727 | 1,202,727 | 188 | text-generation |
| 63 | zai-org/GLM-5-FP8 | zai-org | mit | Not listed | 3014393 | 1,294,393 | 172 | text-generation |
| 86 | openai-community/gpt2-medium | openai-community | mit | Not listed | 2948969 | 948,969 | 200 | text-generation |
| 78 | Qwen/Qwen2.5-1.5B | Qwen | apache-2.0 | 1.5B | 2805041 | 1,045,041 | 176 | text-generation |
| 40 | Qwen/Qwen3-4B-Base | Qwen | apache-2.0 | 4B | 2758692 | 1,888,692 | 87 | text-generation |
| 65 | bigscience/bloomz-560m | bigscience | bigscience-bloom-rail-1.0 | 560M | 2603636 | 1,233,636 | 137 | text-generation |
| 41 | Qwen/Qwen3-0.6B-FP8 | Qwen | apache-2.0 | 0.6B | 2475388 | 1,885,388 | 59 | text-generation |
| 84 | Qwen/Qwen2.5-Coder-14B-Instruct | Qwen | apache-2.0 | 14B | 2469195 | 959,195 | 151 | text-generation |
| 50 | apple/OpenELM-1_1B-Instruct | apple | apple-amlr | 1B | 2303368 | 1,553,368 | 75 | text-generation |
| 62 | Qwen/Qwen2.5-32B-Instruct-AWQ | Qwen | apache-2.0 | 32B | 2293139 | 1,303,139 | 99 | text-generation |
| 94 | deepseek-ai/DeepSeek-V2-Lite-Chat | deepseek-ai | other | Not listed | 2249670 | 879,670 | 137 | text-generation |
| 38 | Qwen/Qwen2.5-14B-Instruct-AWQ | Qwen | apache-2.0 | 14B | 2238183 | 1,898,183 | 34 | text-generation |
| 92 | Qwen/Qwen3-Reranker-4B | Qwen | apache-2.0 | 4B | 2198507 | 888,507 | 131 | text-ranking |
| 59 | nvidia/Kimi-K2.5-NVFP4 | nvidia | other | Not listed | 2124705 | 1,314,705 | 81 | text-generation |
| 33 | hmellor/tiny-random-LlamaForCausalLM | hmellor | Not listed | Not listed | 2107605 | 2,107,605 | 0 | text-generation |
| 71 | thuml/sundial-base-128m | thuml | apache-2.0 | 128M | 1886447 | 1,136,447 | 75 | time-series-forecasting |
| 48 | Andycurrent/Gemma-3-1B-it-GLM-4.7-Flash-Heretic-Uncensored-Thinking_GGUF | Andycurrent | gemma | 1B | 1817414 | 1,637,414 | 18 | text-generation |